AI Beyond the Cloud: Hacking LLMs for Fun, Privacy, and Profit

This meetup is your practical deep dive into the world of Large Language Models. You'll learn how to run powerful, private AI on your own commodity hardware using lightweight models and quantization techniques — no huge AWS bill required. Then, take that knowledge to the next level by building your own agentic pair programmer that's packed with personality and can directly meddle with your code files. Join us to dive into the tools for local, private LLM deployment and get inspired to create a truly dysfunctional (and useful!) digital sidekick.

Walk-in: 17:15
Food: 17:30 - 18:00
First talk (Jeroen Resoort): 18:15 - 19:00
Second talk (Alexander Chatzizacharias): 19:15 - 20:00

Running LLMs on Commodity Hardware: Private, Practical, and Powerful (Jeroen Resoort)

Large Language Models (LLMs) are often seen as requiring expensive GPUs or paid cloud services – but that’s not always true. In this talk, I’ll show you how to run impressive LLMs locally, on affordable consumer-grade hardware. We’ll cover lightweight models, quantization techniques, and tooling that make it feasible to run modern AI privately and securely without breaking the bank. Expect practical tips, live demos, and a clear path to bringing powerful AI capabilities into your own environment — no datacenter (or huge AWS bill) required.

You’ll leave this session with a solid understanding of:

• What types of LLMs can run on CPUs or modest GPUs
• Key techniques like quantization and model pruning
• Tools and libraries that simplify local deployment
• How to maintain privacy and control by avoiding cloud dependencies
• Where to find and how to fine-tune open-source model

How to build your own fun and absurd pair programmer (Alexander Chatzizacharias)

Tired of AI assistants that are always so boring and soulless? Alexander was. So, he decided to build his own. An AI assistant with personality, flair, and a healthy dose of sarcasm. Imagine a pair programmer that offers sarcastic feedback, makes absurd suggestions, and threatens to blow up your code when it disagrees with your changes. And when things get too quiet, it might even challenge you to a game of tic-tac-toe.

This session is for anyone who believes the best way to learn new technologies is by playfully breaking them. If you’re curious about LLMs and agents beyond the typical use cases, this talk is for you. You’ll leave with practical insights into building your own agentic LLM workflows using Spring Boot, vector databases, and locally running models. Alexander will talk about Retrieval-Augmented Generation (RAG) flows that feed LLMs the right context, multi-vector search for fast context retrieval, and Model Context Protocol (MCP) integrations that let the assistant directly meddle with your file system.

Come to learn, chuckle, and get inspired to create your own dysfunctional digital sidekick.